© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78606
    Prev
    Next
    INDEX
    Explanations

    terms related to product quality and efficacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unint
    -0.06
    æľ
    -0.06
     arena
    -0.05
    eil
    -0.05
    rates
    -0.05
     Millenn
    -0.05
    onda
    -0.05
    lub
    -0.05
    ibility
    -0.05
     unc
    -0.05
    POSITIVE LOGITS
     content
    0.09
    (contents
    0.09
     contents
    0.09
    Contained
    0.09
     conten
    0.09
     contained
    0.09
     chứa
    0.09
    Content
    0.08
    CONTENT
    0.08
    _Content
    0.08
    Activations Density 0.015%

    No Known Activations